pre-push

pre-push is a command for Claude Code from thapaliyabikendra/ai-artifacts. It costs 0 tokens per session (1,301 once invoked), scanned A, original, Apache-2.0.

A read-only security check that runs before code is pushed to Git, the version-control system. It reports security issues and blocks the push only for critical findings.

In plain words
What is it for?
Use it for quick scans of small changes, warnings for less serious findings, and an optional mode that reports critical issues without blocking the push.
Why use it?
It catches the most serious security problems at the last step before changes leave the local repository, while allowing the push when the scan is slow or incomplete.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/thapaliyabikendra/ai-artifacts/pre-push
Clone the repo
git clone --depth 1 https://github.com/thapaliyabikendra/ai-artifacts

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pre-push

README.md
[![agentmods](https://agentmods.dev/badge/commands/thapaliyabikendra/ai-artifacts/pre-push.svg)](https://agentmods.dev/commands/thapaliyabikendra/ai-artifacts/pre-push)
Your own site
<a href="https://agentmods.dev/commands/thapaliyabikendra/ai-artifacts/pre-push"><img src="https://agentmods.dev/badge/commands/thapaliyabikendra/ai-artifacts/pre-push.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,301 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01301
Opus 5 $0.00000 $0.00651
Sonnet 5 $0.00000 $0.00260
Haiku 4.5 $0.00000 $0.00130

Measured 6d ago against content hash b8d262610631, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pre-push scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/review/pre-push.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pre-Push Security Scan

Fast, focused security check before pushing. Blocks only on CRITICAL issues.

Arguments: $ARGUMENTS Target: < 30 seconds execution

Constraints (MUST follow)

  1. NO agent spawning - Do not use Task tool
  2. NO writing - Read-only analysis only
  3. NO Bash execution - Use only Read, Glob, Grep
  4. NO external calls - No WebFetch, WebSearch
  5. 30-second limit - If analysis incomplete, exit 0 (allow push)
  6. CRITICAL only blocks - HIGH/MEDIUM/LOW are warnings only
  7. Skip large diffs - If >200 lines changed, exit 0 with warning

Behavior

Condition Exit Code Effect
CRITICAL found (blocking mode) 2 Blocks push
CRITICAL found + --no-block 0 Warning only
HIGH/MEDIUM/LOW found 0 Warning only
No issues 0 Clean pass
Error/timeout 0 Allow push (fail-safe)
>200 lines changed 0 Skip with warning

Execution

Step 1: Parse Arguments

BASE_BRANCH = --base argument OR "origin/develop"
NO_BLOCK = true if --no-block present

Step 2: Get Changed Files

Use Grep to find changed file list from git status or use Glob to identify recently modified files.

Classify by extension:

  • Backend: *.cs, *.csproj
  • Frontend: *.ts, *.tsx, *.js, *.jsx

Step 3: Check Scope

If >20 files OR >200 lines changed:

⚠️  Large diff detected ({N} files, ~{M} lines)
    Skipping pre-push review. Consider smaller commits.

✅ Push allowed (scope too large for fast review)

Exit 0 immediately.

Step 4: Security Scan (Inline Checklist)

Read each changed file and scan for these patterns ONLY:

🔴 CRITICAL (Blocks Push)
Check Pattern to Find Example
Missing Auth Public mutation method without [Authorize] public async Task Create( without auth
Hardcoded Secret password=, apikey=, secret=, connection strings "Password=admin123"
SQL Injection String concat in SQL $"SELECT * FROM {table}"
Exposed Credentials .env files, appsettings.*.json with real values Committed secrets

Read the full file on GitHub · 200 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 200 lines · 0 tokens per session scan A b8d262610631

Subscribe to this mod's changes

pre-push is a command published in the GitHub repository thapaliyabikendra/ai-artifacts (24 stars, last pushed 5mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,301 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.